{"id":"https://openalex.org/W4415036188","doi":"https://doi.org/10.48550/arxiv.2505.20693","title":"Phir Hera Fairy: An English Fairytaler is a Strong Faker of Fluent Speech in Low-Resource Indian Languages","display_name":"Phir Hera Fairy: An English Fairytaler is a Strong Faker of Fluent Speech in Low-Resource Indian Languages","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W4415036188","doi":"https://doi.org/10.48550/arxiv.2505.20693"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.20693","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20693","pdf_url":"https://arxiv.org/pdf/2505.20693","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.20693","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106912741","display_name":"Praveen Srinivasa Varadhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Varadhan, Praveen Srinivasa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106912740","display_name":"Srija Anand","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anand, Srija","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119938400","display_name":"Soma Siddhartha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddhartha, Soma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050036814","display_name":"Mitesh M. Khapra","orcid":"https://orcid.org/0009-0008-3687-9922"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khapra, Mitesh M.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5106912741"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13029","display_name":"South Asian Studies and Conflicts","score":0.6510999798774719,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13029","display_name":"South Asian Studies and Conflicts","score":0.6510999798774719,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5723000168800354,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/polyglot","display_name":"Polyglot","score":0.7455999851226807},{"id":"https://openalex.org/keywords/indian-english","display_name":"Indian English","score":0.5713000297546387},{"id":"https://openalex.org/keywords/hera","display_name":"HERA","score":0.4345000088214874},{"id":"https://openalex.org/keywords/british-english","display_name":"British English","score":0.4307999908924103},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.3621000051498413},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.35910001397132874}],"concepts":[{"id":"https://openalex.org/C2780239667","wikidata":"https://www.wikidata.org/wiki/Q2102850","display_name":"Polyglot","level":2,"score":0.7455999851226807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563000082969666},{"id":"https://openalex.org/C2778443833","wikidata":"https://www.wikidata.org/wiki/Q1348800","display_name":"Indian English","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5163999795913696},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.510699987411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105999708175659},{"id":"https://openalex.org/C2779762263","wikidata":"https://www.wikidata.org/wiki/Q1054761","display_name":"HERA","level":3,"score":0.4345000088214874},{"id":"https://openalex.org/C2779855358","wikidata":"https://www.wikidata.org/wiki/Q7979","display_name":"British English","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3479999899864197},{"id":"https://openalex.org/C2780411076","wikidata":"https://www.wikidata.org/wiki/Q5462653","display_name":"Fluent","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.28279998898506165}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.20693","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20693","pdf_url":"https://arxiv.org/pdf/2505.20693","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.20693","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.20693","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.20693","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20693","pdf_url":"https://arxiv.org/pdf/2505.20693","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415036188.pdf","grobid_xml":"https://content.openalex.org/works/W4415036188.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"What":[0],"happens":[1],"when":[2],"an":[3],"English":[4,15,38,50,89],"Fairytaler":[5],"is":[6,67],"fine-tuned":[7],"on":[8,40,46],"Indian":[9,21,41,48,58],"languages?":[10],"We":[11,30],"evaluate":[12],"how":[13],"the":[14,64],"F5-TTS":[16],"model":[17],"adapts":[18],"to":[19,52,79],"11":[20],"languages,":[22,104],"measuring":[23],"polyglot":[24],"fluency,":[25],"voice-cloning,":[26],"style-cloning,":[27],"and":[28,43,49,63,109,126],"code-mixing.":[29],"compare:":[31],"(i)":[32],"training":[33],"from":[34],"scratch,":[35],"(ii)":[36],"fine-tuning":[37,45],"F5":[39],"data,":[42],"(iii)":[44],"both":[47],"data":[51,59,137],"prevent":[53],"forgetting.":[54],"Fine-tuning":[55],"with":[56],"only":[57],"proves":[60],"most":[61],"effective":[62],"resultant":[65],"IN-F5":[66,119],"a":[68,112,129],"near-human":[69],"polyglot;":[70],"that":[71],"enables":[72],"speakers":[73],"of":[74],"one":[75],"language":[76],"(e.g.,":[77,84],"Odia)":[78],"fluently":[80],"speak":[81],"in":[82,94,101],"another":[83],"Hindi).":[85],"Our":[86],"results":[87],"show":[88,118],"pretraining":[90],"aids":[91],"low-resource":[92,103],"TTS":[93,134],"reaching":[95],"human":[96],"parity.":[97],"To":[98],"aid":[99],"progress":[100],"other":[102],"we":[105,117],"study":[106],"data-constrained":[107],"setups":[108],"arrive":[110],"at":[111],"compute":[113],"optimal":[114],"strategy.":[115],"Finally,":[116],"can":[120],"synthesize":[121],"unseen":[122],"languages":[123],"like":[124],"Bhojpuri":[125],"Tulu":[127],"using":[128],"human-in-the-loop":[130],"approach":[131],"for":[132],"zero-resource":[133],"via":[135],"synthetic":[136],"generation.":[138]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}